• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.515-522
• /
• 2021

In this paper, we present and analyze a method of applying a machine learning to ultrasonic test signals for constant monitoring of the welding faults in a tubular steel tower. For the machine learning, feature selection based on genetic algorithm and fault signal classification using a support vector machine have been used. In the feature selection, the peak value, histogram lower bound, and normal negative log-likelihood from 30 features are selected. Those features clearly indicate the difference of signals according to the depth of faults. In addition, as a result of applying the selected features to the support vector machine, it has been possible to perfectly distinguish between the regions with and without faults. Hence, it is expected that the results of this study will be useful in the development of an early detection system for fault growth based on ultrasonic signals and in the energy transmission related industries in the future.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.42-45
• /
• 2011

3차원 영상과 더불어 스테레오 영상의 관심이 늘어남에 따라 좌, 우 영상의 매칭을 통해 변이를 추정하는 연구가 활발하게 진행되고 있다. 본 논문에서는 변이 추정을 위해 많이 사용되는 영역 기반(Block-based)의 전체 탐색 알고리즘보다 효율적이고 계산량이 적은 변이 추정을 할 수 있도록 변이 탐색 범위를 제공해주는 방법을 제안한다. 제안되는 알고리즘은 해리스 코너 포인트 검출기를 이용하여 좌, 우 영상 각각의 특징 점을 추출한 후, 특징 점의 정보를 이용하여 스테레오 매칭을 한다. 스테레오 매칭 시 이를 히스토그램화 하여 좌, 우 영상의 변이 추정을 위한 탐색 범위를 제공한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.676-678
• /
• 2005

디지털 비디오에 있어서 멀티미디어 데이터베이스 및 검색 시스템 구축을 하기 위해서는 비디오를 여러개의 장면으로 분할하는 기술이 요구된다. 본 논문에서는 다양한 종류의 장면 전환을 검출하기 위해 기존의 규칙기반이 아닌 신경망 이론을 접목하여 자율학습과 실수값 입력이 가능한 ART2를 이용하였다. 매프레임마다 발생할 수 있는 변동의 폭을 줄이기 위해 MPEG 동영상의 DC에 해당하는 값만을 이용하고, 프레임마다 색상의 분산값을 이용하여 Plateaus 구간을 검출한 다음 Plateaus 구간에 해당하는 프레임들에 대해서만 프레임차이, 히스토그램차이, 상관계수 등의 특징치를 추출하여 ART2에 특징벡터를 입력하여 장면 전환을 검출하였다.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.1-14
• /
• 2011

While the circulation of images become active, various requirements to manage increasing database are raised. The content-based technology is one of methods to satisfy these requirements. The image is represented by feature vectors extracted by various methods in the content-based technology. The global feature method insures fast matching speed because the feature vector extracted by the global feature method is formed into a standard shape. The global feature extraction methods are classified into two categories, the spatial feature extraction and statistical feature extraction. And each group is divided by what kind of information is used, color feature or gray scale feature. In this paper, we introduce various global feature extraction technologies and compare their performance by accuracy, recall-precision graph, ANMRR, feature vector size and matching time. According to the experiments, the spatial features show good performance in non-geometrical modifications, and the extraction technologies that use color and histogram feature show the best performance.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.203-212
• /
• 2015

This paper proposes a traffic sign recognition method in real road environments. The video stream in driving environments has two different characteristics compared to a general object video stream. First, the number of traffic sign types is limited and their shapes are mostly simple. Second, the camera cannot take clear pictures in the road scenes since there are many illumination changes and weather conditions are continuously changing. In this paper, we improve a modified census transform(MCT) to extract features effectively from the road scenes that have many illumination changes. The extracted features are collected by histograms and are transformed by the dense descriptors into very high dimensional vectors. Then, the high dimensional descriptors are encoded into a low dimensional feature vector by Fisher-vector coding and Gaussian Mixture Model. The proposed method shows illumination invariant detection and recognition, and the performance is sufficient to detect and recognize traffic signs in real-time with high accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.1
• /
• pp.43-50
• /
• 2016

This paper introduces an appearance-based facial expression recognition method using ASM landmarks which is used to acquire a detailed face region. In particular, EHMM-based algorithm and SVM classifier with histogram feature are employed to appearance-based facial expression recognition, and performance evaluation of proposed method was performed with CK and JAFFE facial expression database. In addition, performance comparison was achieved through comparison with distance-based face normalization method and a geometric feature-based facial expression approach which employed geometrical features of ASM landmarks and SVM algorithm. As a result, the proposed method using ASM-based face normalization showed performance improvements of 6.39% and 7.98% compared to previous distance-based face normalization method for CK database and JAFFE database, respectively. Also, the proposed method showed higher performance compared to geometric feature-based facial expression approach, and we confirmed an effectiveness of proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.429-440
• /
• 2014

The iris recognition is a biometrics technology to extract and code an unique iris feature from human eye image. Also, it includes the technology to compare with other's various iris stored in the system. On the other hand, eyelashes in iris image are a external factor to affect to recognition rate of iris. If eyelashes are not removed exactly from iris area, there are two false recognitions that recognize eyelashes to iris features or iris features to eyelashes. Eventually, these false recognitions bring out a lot of loss in iris informations. In this paper, in order to solve that problems, we removed eyelashes by gabor filter that using for analysis of frequency feature and improve preservation rate of iris informations. By novel method to extract various features on iris area using angle, frequency, and gaussian parameter on gabor filter that is one of the filters for analysing frequency feature for an image, we could remove accurately eyelashes with various lengths and shapes. As the result, proposed method represents that improve about 4% than previous methods using GMM or histogram analysis in iris preservation rate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.341-343
• /
• 2012

본 논문에서는 기존의 특징점 기반 객체 인식 방법의 확장으로 보완적 특징점 기반의 컬러 정보를 포함하는 기술자를 활용하는 객체 인식 방법을 제안한다. 제안하는 방법은 무늬가 적은 객체에서도 에지의 위치를 샘플링함으로써 보완적 특징점을 생성해 낸다. 그리고 검출된 보완적 특징점으로부터 얻어지는 그레이 값 변화도방향 정보와 컬러 정보를 가지고 있는 기술자를 생성한다. 그리고 생성된 기술자를 객체 단위로 묶어 낼 수 있도록 하는 코드북(Codebook)을 학습함으로써 각 객체를 구분해 낼 수 있는 강건한 히스토그램를 생성한다. 생성된 코드북을 활용함으로써 제안하는 방법은 객체의 크기 및 환경 변화, 3차원 회전의 경우에도 기존의 방법보다 강건하게 인식한다. 실험 결과 제안하는 방법은 75.8% 인식률을 보이는 것을 확인하였다. 이 방법은 증강현실 응용에 정보 제시를 위해 가장 먼저 이루어지는 핵심 기술로써 활용될 수 있다.

• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.281-288
• /
• 2009

This paper proposes a novel algorithm for the efficient classification and annotation of medical images, especially X-ray images. Since X-ray images have a bright foreground against a dark background, we need to extract the different visual descriptors compare with general nature images. In this paper, a Color Structure Descriptor (CSD) based on Harris Corner Detector is only extracted from salient points, and an Edge Histogram Descriptor (EHD) used for a textual feature of image. These two feature vectors are then applied to a multi-class Support Vector Machine (SVM), respectively, to classify images into one of 20 categories. Finally, an image has the Annotation Code Array based on the pre-defined hierarchical relations of categories and priority code order, which is given the several optimal keywords by the Annotation Code Array. Our experiments show that our annotation results have better annotation performance when compared to other method.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1692-1700
• /
• 2009

This paper proposes the direction distribution of surface normal vectors as a feature descriptor of three-dimensional models. Proposed the feature descriptor handles rotation invariance using a principal component analysis(PCA) method, and performs mesh simplification to make it robust and nonsensitive against noise addition. Our method picks samples for the distribution of normal vectors to be proportional to the area of each polygon, applies weight to the normal vectors, and applies interpolation to enhance discrimination so that the information on the surface with less area may be less reflected on composing a feature descriptor. This research measures similarity between models with a L1-norm in the probability density histogram where the distances of feature descriptors are normalized. Experimental results have shown that the proposed method has improved the retrieval performance described in an average normalized modified retrieval rank(ANMRR) by about 17.2% and the retrieval performance described in a quantitative discrimination scale by 9.6%~17.5% as compared to the existing method.